LongCat 2.0 vs Fugu Ultra
LongCat 2.0 costs 25.0x less per output token than Fugu Ultra ($1.20 vs $30.00 per million). Updated October 23, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $1.20
- Coding
- No data
- Overall
- No data
- Output $/M
- $30.00
LongCat 2.0 or Fugu Ultra: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick LongCat 2.0 for output tokens 25.0x cheaper ($1.20 vs $30.00 per million) and a larger context window (1.05M against 1M tokens).
No benchmark has tested both yet. LongCat 2.0 has results on AA Coding Index, SciCode and ALE-Bench; Fugu Ultra has none yet. Compare them on price and context instead.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only LongCat 2.0 has a AA Intelligence Index result, 19.1.
Directional only
Agentic work
AA Agentic Index
No call
Only LongCat 2.0 has a AA Agentic Index result, 14.0.
Directional only
Long documents
Listed context window
LongCat 2.0
LongCat 2.0 takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
LongCat 2.0
LongCat 2.0 $0.0009, Fugu Ultra $0.020 per turn.
List prices
At a glance
- Coding index
- LongCat 2.0 not benchmarked, Fugu Ultra not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- LongCat 2.0 $1.20 against Fugu Ultra $30.00 per million output tokens, 25.0x apart.
- Context window
- LongCat 2.0 takes 1.05M tokens, Fugu Ultra 1M.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index3 boards measured
| Benchmark | LongCat 2.0 | Fugu Ultra | Leader |
|---|---|---|---|
| AA Coding Index | 45.3 | Not measured | Only LongCat 2.0 measured |
| SciCode | 36.3% | Not measured | Only LongCat 2.0 measured |
| ALE-Bench | 793.5 | Not measured | Only LongCat 2.0 measured |
| Neither model has a result on the other 40 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | LongCat 2.0 | Fugu Ultra | Leader |
|---|---|---|---|
| AA Intelligence Index | 19.1 | Not measured | Only LongCat 2.0 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | LongCat 2.0 | Fugu Ultra | Leader |
|---|---|---|---|
| AA Agentic Index | 14.0 | Not measured | Only LongCat 2.0 measured |
| Neither model has a result on the other 41 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | LongCat 2.0 | Fugu Ultra | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 78.0% | Not measured | Only LongCat 2.0 measured |
| Humanity's Last Exam (Artificial Analysis run) | 33.7% | Not measured | Only LongCat 2.0 measured |
| Neither model has a result on the other 21 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | LongCat 2.0 | Fugu Ultra | Leader |
|---|---|---|---|
| Long context reasoning (AA-LCR) | 65.0% | Not measured | Only LongCat 2.0 measured |
| Neither model has a result on the other 47 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
LongCat 2.0 costs less
Repository review
50K input + 3K output tokens
LongCat 2.0 costs less
Agent loop
200K input + 10K output tokens
LongCat 2.0 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Meituan LongCat 2.0 | Sakana Fugu Ultra |
|---|---|---|
| Maker | Meituan | Sakana |
| Weights | Open weights | No public weights listed |
| Released | July 20, 2026 | June 24, 2026 |
| Context window | 1.05M | 1M |
| Input $/Mtok | $0.30 | $5.00 |
| Output $/Mtok | $1.20 | $30.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is LongCat 2.0 better than Fugu Ultra for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick LongCat 2.0 for output tokens 25.0x cheaper ($1.20 vs $30.00 per million) and a larger context window (1.05M against 1M tokens).
Which is cheaper, LongCat 2.0 or Fugu Ultra?
LongCat 2.0 costs $0.30 per million input tokens and $1.20 per million output tokens; Fugu Ultra costs $5.00 and $30.00. Cost per solved task is known for neither of them.
Which has the bigger context window, LongCat 2.0 or Fugu Ultra?
LongCat 2.0, with 1.05M tokens against 1M.
Has any benchmark tested both LongCat 2.0 and Fugu Ultra?
No benchmark has tested both yet. LongCat 2.0 has results on AA Coding Index, SciCode and ALE-Bench; Fugu Ultra has none yet. Compare them on price and context instead. Data as of October 23, 2026.